CoreCognition Image + Video Toolusing: leaderboard

CoreCognition Image + Video Toolusing — CoreCognition native component accuracy and reported mean. Image+Video, image-only and single-image populations are separate; no pooling or replacement across cohorts. Metric: Accuracy (%). Source: https://grow-ai-like-a-child.github.io/CoreCognition/leaderboard

Metric: Accuracy (%). Source: grow-ai-like-a-child.github.io. Saturation forecast: Estimated already saturated. 120 models tracked. Updated 16 Nov 2026.

Top models

#ModelScoreOverall rank
1Grok 2 (1212)99.21#1072
2GPT-4 Turbo98.75#999
3O1 (2024-12-17)98.16#313
4Gemini 1.5 Pro98.09#1061
5Claude 3.5 Sonnet (20240620)97.96#692
6Qwen 2.5 VL 72B Instruct97.96#848
7Qwen-VL-Max-2025-01-2597.96
8Gemma 3 27B (IT)97.52#1322
9GPT-4o96.91#744
10Pixtral-12B-240996.91#2705
11Qwen-VL-Plus-2025-01-2596.91
12Qwen 2.5 VL 7B Instruct96.78#1867
13GPT-4o Mini96.12#1658
14Qwen 2.5 VL 3B Instruct96.05#2562
15VILA1.5-40B95.92#3222

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-plus-video-toolusing · How It Works · Data refreshed daily, snapshot 2026-11-16.